Papers
Wed 7 Dec 2022
167 papers
- Talking Head Generation with Probabilistic Audio-to-Visual Diffusion PriorsDiffusion models → Audio, speech and music
- Learning Graph Search HeuristicsOffline RL and imitation learning from data → Imitation learning methods
- Tight Performance Guarantees of Imitator Policies with Continuous ActionsOffline RL and imitation learning from data → Imitation learning methods
- Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- One Sample Diffusion Model in Projection Domain for Low-Dose CT ImagingDiffusion models → Medical imaging and segmentation
- Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-EnsembleOffline RL and imitation learning from data → Imitation learning methods
- The problem with AI consciousness: A neurogenetic case against synthetic sentience
- Encoder-Decoder Network with Guided Transmission Map: Architecture
- Hierarchical multimodal transformers for Multi-Page DocVQA
- Adaptive Self-Training for Object Detection
- Testing Human Ability To Detect Deepfake Images of Human Faces
- Deep conv-attention model for diagnosing left bundle branch block from 12-lead electrocardiograms
- Review of Ansatz Designing Techniques for Variational Quantum Algorithms
- Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability
- Physics-constrained deep learning postprocessing of temperature and humidity
- Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction
- Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization
- Fraud Analytics: A Decade of Research -- Organizing Challenges and Solutions in the Field
- Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers
- EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points
- ViTPose++: Vision Transformer for Generic Body Pose Estimation
- Domain generalization of 3D semantic segmentation in autonomous driving
- A parallelizable model-based approach for marginal and multivariate clustering
- RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts
- Zero-Shot Transfer Learning for Structural Health Monitoring using Generative Adversarial Networks and Spectral Mapping
- TweetDrought: A Deep-Learning Drought Impacts Recognizer based on Twitter Data
- DDoD: Dual Denial of Decision Attacks on Human-AI Teams
- Unsupervised language models for disease variant prediction
- Unsupervised Deep Learning for AC Optimal Power Flow via Lagrangian Duality
- Counterfactuals for the Future
- Multimodal Vision Transformers with Forced Attention for Behavior Analysis
- Few-shot Medical Image Segmentation with Cycle-resemblance Attention
- CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework
- FSID: Fully Synthetic Image Denoising via Procedural Scene Generation
- Short term prediction of demand for ride hailing services: A deep learning approach
- Experiences from the MediaEval Predicting Media Memorability Task
- Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning
- Learning Polysemantic Spoof Trace: A Multi-Modal Disentanglement Network for Face Anti-spoofing
- An Efficient Evolutionary Deep Learning Framework Based on Multi-source Transfer Learning to Evolve Deep Convolutional Neural Networks
- Low Variance Off-policy Evaluation with State-based Importance Sampling
- Transfer learning for chemically accurate interatomic neural network potentials
- Analysis of Drug repurposing Knowledge graphs for Covid-19
- Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve
- Pre-Training With Scientific Text Improves Educational Question Generation
- Deep Learning for Brain Age Estimation: A Systematic Review
- Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task
- Learning on Graphs for Mineral Asset Valuation Under Supply and Demand Uncertainty
- X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
- Teaching Matters: Investigating the Role of Supervision in Vision Transformers
- See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation
- Phase2vec: Dynamical systems embedding with a physics-informed convolutional network
- Point Cloud Registration of non-rigid objects in sparse 3D Scans with applications in Mixed Reality
- Computing linear sections of varieties: quantum entanglement, tensor decompositions and beyond
- NeRFEditor: Differentiable Style Decomposition for Full 3D Scene Editing
- Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations
- PaDPaF: Partial Disentanglement with Partially-Federated GANs
- Discovering Latent Knowledge in Language Models Without Supervision
- Unsupervised Domain Adaptation for Semantic Segmentation using One-shot Image-to-Image Translation via Latent Representation Mixing
- iQuery: Instruments as Queries for Audio-Visual Sound Separation
- Robustness of Learning from Task Instructions
- Toward Multi-Service Edge-Intelligence Paradigm: Temporal-Adaptive Prediction for Time-Critical Control over Wireless
- Towards Explainable Motion Prediction using Heterogeneous Graph Representations
- A Frequency-Structure Approach for Link Stream Analysis
- Unsupervised spectral-band feature identification for optimal process discrimination
- Stochastic Rising Bandits
- Reconciling a Centroid-Hypothesis Conflict in Source-Free Domain Adaptation
- A Neural Network Approach for Selecting Track-like Events in Fluorescence Telescope Data
- Tight bounds for maximum ℓ1-margin classifiers
- Expressive architectures enhance interpretability of dynamics-based neural population models
- Generalized Gradient Flows with Provable Fixed-Time Convergence and Fast Evasion of Non-Degenerate Saddle Points
- Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning
- GAMMA: Generative Augmentation for Attentive Marine Debris Detection
- GLeaD: Improving GANs with A Generator-Leading Task
- Memorization of Named Entities in Fine-tuned BERT Models
- Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review
- FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation
- Tiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior
- Optimal transport map estimation in general function spaces
- Overview Of Satellite Image Recognition Models
- Reconstructing Training Data from Model Gradient, Provably
- Intervening With Confidence: Conformal Prescriptive Monitoring of Business Processes
- Development Of A Fire Detection System On Satellite Images
- Leveraging Structure for Improved Classification of Grouped Biased Data
- Gaussian Radar Transformer for Semantic Segmentation in Noisy Radar Data
- Neighborhood Adaptive Estimators for Causal Inference under Network Interference
- Face Presentation Attack Detection
- Face Forgery Detection Based on Facial Region Displacement Trajectory Series
- Unsupervised Flood Detection on SAR Time Series
- Concentration Phenomenon for Random Dynamical Systems: An Operator Theoretic Approach
- Multi-Objective Linear Ensembles for Robust and Sparse Training of Few-Bit Neural Networks
- Learning Double-Compression Video Fingerprints Left from Social-Media Platforms
- M3ST: Mix at Three Levels for Speech Translation
- Node-oriented Spectral Filtering for Graph Neural Networks
- Cyclically Disentangled Feature Translation for Face Anti-spoofing
- Towards Automatic Cetacean Photo-Identification: A Framework for Fine-Grain, Few-Shot Learning in Marine Ecology
- Non-uniform Sampling Strategies for NeRF on 360textdegree images
- An Intuitive and Unconstrained 2D Cube Representation for Simultaneous Head Detection and Pose Estimation
- G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks
- DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing
- On the Global Solution of Soft k-Means
All 167
- ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
- Multiple Object Tracking Challenge Technical Report for Team MT_IoT
- Tag Embedding and Well-defined Intermediate Representation improve Auto-Formulation of Problem Description
- Learning rigid dynamics with face interaction graph networks
- Optimizing a Digital Twin for Fault Diagnosis in Grid Connected Inverters -- A Bayesian Approach
- SeqLink: A Robust Neural-ODE Architecture for Modelling Partially Observed Time Series
- GraphLearner: Graph Node Clustering with Fully Learnable Augmentation
- Low-Resource End-to-end Sanskrit TTS using Tacotron2, WaveGlow and Transfer Learning
- Talking About Large Language Models
- Support Vector Machine for Determining Euler Angles in an Inertial Navigation System
- MetaStackVis: Visually-Assisted Performance Evaluation of Metamodels
- Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- Curiosity creates Diversity in Policy Search
- Towards Fleet-wide Sharing of Wind Turbine Condition Information through Privacy-preserving Federated Learning
- Criteria for Classifying Forecasting Methods
- MOB-FL: Mobility-Aware Federated Learning for Intelligent Connected Vehicles
- AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation
- Site Assessment and Layout Optimization for Rooftop Solar Energy Generation in Worldview-3 Imagery
- FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip Training
- Truthful Meta-Explanations for Local Interpretability of Machine Learning Models
- Ensuring Visual Commonsense Morality for Text-to-Image Generation
- WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition
- LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving
- Learning Continuous Depth Representation via Geometric Spatial Aggregator
- BoxPolyp:Boost Generalized Polyp Segmentation Using Extra Coarse Bounding Box Annotations
- A Generative Approach for Script Event Prediction via Contrastive Fine-tuning
- Metric Elicitation; Moving from Theory to Practice
- SimVTP: Simple Video Text Pre-training with Masked Autoencoders
- Bringing the Algorithms to the Data -- Secure Distributed Medical Analytics using the Personal Health Train (PHT-meDIC)
- Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information
- PyGFI: Analyzing and Enhancing Robustness of Graph Neural Networks Against Hardware Errors
- Tree DNN: A Deep Container Network
- Optimizing Multiple Simultaneous Objectives for Voting and Facility Location
- MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy
- Sequential Predictive Conformal Inference for Time Series
- PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels
- Distributed Interaction Graph Construction for Dynamic DCOPs in Cooperative Multi-agent Systems
- Dock2D: Synthetic data for the molecular recognition problem
- Fallen Angel Bonds Investment and Bankruptcy Predictions Using Manual Models and Automated Machine Learning
- Tracking the Dynamics of the Tear Film Lipid Layer
- Dynamic Graph Node Classification via Time Augmentation
- Integration of Pre-trained Protein Language Models into Geometric Deep Learning Networks
- Bi-LSTM Price Prediction based on Attention Mechanism
- UI Layers Group Detector: Grouping UI Layers via Text Fusion and Box Attention
- Improve Bilingual TTS Using Dynamic Language and Phonology Embedding
- Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer
- Learning Action-Effect Dynamics from Pairs of Scene-graphs
- Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning
- Capturing the Flow of Art History
- JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset
- Slimmable Pruned Neural Networks
- DREAM: A Dynamic Scheduler for Dynamic Real-time Multi-model ML Workloads
- Artificial Intelligence Security Competition (AISC)
- A Flexible Nadaraya-Watson Head Can Offer Explainable and Calibrated Classification
- SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems
- SSDNeRF: Semantic Soft Decomposition of Neural Radiance Fields
- Towards using Few-Shot Prompt Learning for Automating Model Completion
- MIMO-DBnet: Multi-channel Input and Multiple Outputs DOA-aware Beamforming Network for Speech Separation
- Analysis and Utilization of Entrainment on Acoustic and Emotion Features in User-agent Dialogue
- Learning to Select Prototypical Parts for Interpretable Sequential Data Modeling
- A Temporal Graph Neural Network for Cyber Attack Detection and Localization in Smart Grids
- Generating Real-Time Strategy Game Units Using Search-Based Procedural Content Generation and Monte Carlo Tree Search
- DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition
- Improving Deep Localized Level Analysis: How Game Logs Can Help
- General multi-fidelity surrogate models: Framework and active learning strategies for efficient rare event simulation
- Learning State Transition Rules from Hidden Layers of Restricted Boltzmann Machines